Article Per Year (5 Year)
p-Index From 2020 - 2025
1.431
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) JUTI: Jurnal Ilmiah Teknologi Informasi Jurnal Teknologi Informasi dan Ilmu Komputer ELINVO (Electronics, Informatics, and Vocational Education) JURNAL PENGABDIAN KEPADA MASYARAKAT Register: Jurnal Ilmiah Teknologi Sistem Informasi Jurnal Mantik Business Review and Case Studies Jurnal Nasional Teknik Elektro dan Teknologi Informasi
Humasak T. A. Simanjuntak
Institut Teknologi Del
Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Languange, Linguistic, Communication & Media Library & Information Science Social Sciences

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
QUERY RESPONSE TIME COMPARISON NOSQLDB MONGODB WITH SQLDB ORACLE Simanjuntak, Humasak T. A.; Simanjuntak, Lowiska; Situmorang, Goretti; Saragih, Adesty
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 13, No 1, Januari 2015
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v13i1.a392

Abstract

Penyimpanan data saat ini terdapat dua jenis yakni relational database dan non-relational database. Kedua jenis DBMS (Database Managemnet System) tersebut berbeda dalam berbagai aspek seperti per-formansi eksekusi query, scalability, reliability maupun struktur penyimpanan data. Kajian ini memiliki tujuan untuk mengetahui perbandingan performansi DBMS antara Oracle sebagai jenis relational data-base dan MongoDB sebagai jenis non-relational database dalam mengolah data terstruktur. Eksperimen dilakukan untuk mengetahui perbandingan performansi kedua DBMS tersebut untuk operasi insert, select, update dan delete dengan menggunakan query sederhana maupun kompleks pada database Northwind. Untuk mencapai tujuan eksperimen, 18 query yang terdiri dari 2 insert query, 10 select query, 2 update query dan 2 delete query dieksekusi. Query dieksekusi melalui sebuah aplikasi .Net yang dibangun sebagai perantara antara user dengan basis data. Eksperimen dilakukan pada tabel dengan atau tanpa relasi pada Oracle dan embedded atau bukan embedded dokumen pada MongoDB. Response time untuk setiap eksekusi query dibandingkan dengan menggunakan metode statistik. Eksperimen menunjukkan response time query untuk proses select, insert, dan update pada MongoDB lebih cepatdaripada Oracle. MongoDB lebih cepat 64.8 % untuk select query;MongoDB lebihcepat 72.8 % untuk insert query dan MongoDB lebih cepat 33.9 % untuk update query. Pada delete query, Oracle lebih cepat 96.8 % daripada MongoDB untuk table yang berelasi, tetapi MongoDB lebih cepat 83.8 % daripada Oracle untuk table yang tidak memiliki relasi.Untuk query kompleks dengan Map Reduce pada MongoDB lebih lambat 97.6% daripada kompleks query dengan aggregate function pada Oracle.
Survey on Ditenun Application Utilization Through Independent Learning – Independent Campus Program (Merdeka Belajar – Kampus Merdeka) Humasak Tommy Argo Simanjuntak; Arlinta Christy Barus; Samuel Indra Gunawan Situmeang; Arie Satia Dharma
Jurnal Mantik Vol. 5 No. 4 (2022): February: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The policy of Independent Learning - Independent Campus (Merdeka Belajar - Kampus Merdeka: MBKM) by the Ministry of Education, Culture, Research, and Technology provides opportunities for students to gain real work experience in an industrial or professional environment to prepare students in social, cultural, work and technological changes. DiTenun (Digital Tenun Nusantara) responds to this challenge by organizing an independent learning program to accelerate student work readiness while increasing the competitiveness of DiTenun’s industry and products. This study aims to evaluate the successful implementation of MBKM in the development of the DiTenun application. The implementation was analyzed from the perspective of students and application users. This study used a survey research method and a saturated sampling technique. Hypothesis testing showed that the implementation of MBKM program positively affects the development of DiTenun application.
Penilaian Kesamaan Entity Relationship Diagram dengan Algoritme Tree Edit Distance Humasak Simanjuntak; Rosni Lumbantoruan; Wiwin Banjarnahor; Erisha Sitorus; Magdalena Panjaitan; Sintong Panjaitan
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 6 No 1: Februari 2017
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1265.561 KB)

Abstract

Main competency in database learning is ability to design Entity Relationship Diagram (ERD). Generally, lecturer gives task to students to design an ERD with some requirements. These ERDs are then assessed by comparing them with the answers. In practice, the process takes long time and it is possible that the lecturer grades the students inconsistently. Furthermore, plagiarism could be occured without being noticed by the lecturer. This research aims to design and build an application that assess similarity of ERD. The application apply tree edit distance algorithm in checking ERD similarity. ERD is exported into XMI document and then processed using the tree edit distance algorithm. The results show that ERD similarity value depends on number of insert, delete, and rename operation in tree edit distance Algorithm rather than number of difference component.
Business Development of Digital Tenun Nusantara (Ditenun) Using Business Model Canvas and SWOT Analysis Monica Butarbutar; Hansel Septiyan Pasaribu; Noramti Mardianti Manurung; Ricton Samuel Sitorus; Arlinta Christy Barus; Febriani Gultom; Humasak Tommy Argo Simanjuntak; Nancy Panjaitan; Wesly Mailander Siagian
Business Review and Case Studies Vol. 4 No. 2 (2023): BRCS, Vol 4 No 2, August 2023
Publisher : School of Business, IPB University (SB-IPB)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17358/brcs.4.2.144

Abstract

DiTenun is a start-up engaged in traditional woven fabrics. The main product of DiTenun is the technology that can create woven motifs using artificial intelligence. In running the business, DiTenun is still experiencing stagnation in its development so that DiTenun continues to make efforts to develop its business. One of these efforts is to participate in the Kedaireka Matching Fund program offered by the Ministry of Education and Culture. This program requires DiTenun to cooperate with Batikta and Kaldera. To support this collaboration, it is necessary to know Dtenun business model's description to make the collaboration flow more focused. Therefore, this research aimed to discover the description of the DiTenun business model and its business collaboration. Canvas Business Model was used to determine the business strategy and was tested using SWOT planning method to evaluate the project's strengths, weaknesses, opportunities and threats or business speculation. From the BMC (Canvas Business Model) that has been designed for weaving, the company are recommended to further develop it in the elements of several elements. On the key activities element, it can focus on building a community of weavers when marketing expansion is better at selling its products. On the key partner element, it can expand its partners to the ones who can make DiTenun more developed, both in terms of business and production. On key resource elements, they can further develop their technology so that they can produce more perfect motifs and can be much easier for weavers to understand. Another essential thing that DiTenun needs to pay attention to is participating in critical programs to help DiTenun expand its business. Keywords: ditenun, start-up, business model canvas, swot, business development
Two-step convolutional neural network classification of plant disease Lumbantoruan, Rosni; Rajagukguk, Nico; Lubis, Anju Ucok; Claudia, Marwani; Simanjuntak, Humasak
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 1: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i1.pp584-591

Abstract

Indonesia is primarily an agricultural country, with farming being the primary source of income for most of its people. Unfortunately, crop production is vulnerable to plant diseases, which are usually caused by plant pests, resulting in a reduction in both the quantity and quality of the expected harvest. In addition to the large number of classes to predict, detecting and accurately classifying each disease on different plants can be difficult. We believe that limiting the number of classes to identify may improve classification accuracy. Thus, in this research, we propose a new approach, two-step convolutional neural network (CNN), which reduces the number of classes with a two-step classification approach. To begin, we identify the number of classes that can be reduced by categorizing them into different characteristics, namely, plant type classification and plant condition classification. Second, we deal with unbalanced datasets, which can result in poor performance, if overlooked. Finally, we compare the proposed two-step CNN to baseline CNN in terms of efficiency and effectiveness. Extensive experiments show that the two-step CNN outperforms the baselines, CNN and jellyfish-residual network (JF-ResNet), increasing accuracy by 4% and 2% to 99%, respectively. In addition, we also provide a simulation evaluation to ensure that this approach is applicable.
A Benchmark Study of Protein Embeddings in Sequence-Based Classification Simanjuntak, Humasak Tommy Argo; Siahaan, Lamsihar; Margaretha, Patricia Dian; Manurung, Ruth Christine; Purba, Susi; Lumbantoruan, Rosni; Barus, Arlinta; Gonzales, Helen Grace B.
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 9 No. 2 (2024): November 2024
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v9i2.77389

Abstract

Proteins play a vital role in various tissue and organ activities and play a key role in cell structure and function. Humans can produce thousands of proteins, each consisting of tens or hundreds of interconnected amino acids. The sequence of amino acids determines the protein's 3D structure and conformational dynamics, which in turn affects its biological function. Understanding protein function is very important, especially for biological processes at the molecular level. However, extracting or studying features from protein sequences that can predict protein function is still challenging: it takes a long time, is an expensive process, and has yet to be maximized in accuracy, resulting in a large gap between protein sequence and function. Protein embedding is essential in function protein prediction using a deep learning model. Therefore, this study benchmarks three protein embedding models, ProtBert, T5, and ESM-2, as a part of function protein prediction using the LSTM Model. We delve into protein embedding performance and how to leverage it to find optimal embeddings for a given use case. We experimented with the CAFA-5 dataset to see the optimal embedding model in protein function prediction. Experiment results show that ESM-2 outperforms from ProtBert and T5. On training, the accuracy of ESM-2 is above 0.99, almost the same as T5, but still above ProtBert. Furthermore, testing on five samples of protein sequence shows that ESM2 has an average hit rate of 93.33% (100% for four samples and 66.67% for one sample).
DISEMINASI APLIKASI DITENUN BAGI MITRA KELOMPOK TENUN SATAHI SAOLOAN Simanjuntak, Humasak
JURNAL PENGABDIAN KEPADA MASYARAKAT Vol. 31 No. 2 (2025): APRIL-JUNI
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/jpkm.v31i2.65408

Abstract

Kegiatan pengabdian masyarakat ini bertujuan untuk meningkatkan keterampilan dan pengetahuan kelompok penenun Satahi Saoloan dalam memanfaatkan teknologi digital melalui aplikasi DiTenun. Program ini dirancang untuk membantu para penenun menciptakan variasi motif dan desain tenun yang lebih modern, sehingga mereka dapat bersaing dalam industri tenun yang semakin kompetitif. Metodologi yang digunakan mencakup beberapa tahapan: Identifikasi dan Analisis Kebutuhan, Sosialisasi, Pelatihan dan Demonstrasi, Penerapan Teknologi, Pendampingan dan Evaluasi, serta Keberlanjutan Program. Hasil observasi lapangan mengungkapkan sejumlah tantangan utama yang dihadapi penenun adalah Rendahnya pendapatan penenun akibat waktu pembuatan tenun yang lama dan modal yang terbatas; serta Keterbatasan variasi motif dan desain yang menjadi penghambat daya saing. Evaluasi pelaksanaan program menunjukkan adanya peningkatan signifikan dalam pemahaman dan keterampilan penenun menggunakan aplikasi DiTenun. Sebagai salah satu luaran program, para penenun berhasil merancang dan menghasilkan enam motif baru melalui fitur lidi, serta menenun langsung motif-motif tersebut. Kegiatan ini memberikan kontribusi besar dalam mengidentifikasi dan mengatasi tantangan yang dihadapi para penenun. Penggunaan teknologi DiTenun terbukti menjadi solusi inovatif untuk meningkatkan pendapatan sekaligus memperluas variasi motif tenun. Untuk menjamin keberlanjutan program, telah dibentuk tim internal di kalangan penenun Satahi Saoloan sebagai fasilitator untuk memanfaatkan aplikasi ini secara mandiri di masa depan.
Prediksi Single-Step dan Multi-Step Data Cuaca Menggunakan Model Long Short-Term Memory dan Sarima Simanjuntak, Humasak Tommy Argo; Lumbanraja, Amelia; Samosir, Gabriel; Regita
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 2: April 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025129444

Abstract

Prediksi deret waktu pada parameter data cuaca adalah proses memprediksi nilai masa depan berdasarkan pola data historis cuaca. Penelitian ini mengatasi kelemahan penelitian sebelumnya seperti data yang terbatas, jangka waktu prediksi, keterbatasan parameter yang digunakan dalam penelitian serta tidak menggunakan parameter eksternal yang tentunya dapat membantu proses prediksi model menjadi lebih akurat. Penelitian ini menggunakan metode Long Short-Term Memory (LSTM) dan Seasonal AutoRegressive Integrated Moving Average (SARIMA) untuk memprediksi parameter cuaca, seperti tekanan udara, suhu, dan kelembaban relatif, dengan pendekatan single-step dan multi-step ahead. Data bersumber dari BMKG Stasiun Meteorologi Pinangsori, Sibolga, selama 8 tahun, dengan granularity per jam dan per hari. Hasil eksperimen menunjukkan bahwa LSTM dan SARIMA, memiliki keunggulan dalam konteks tertentu. Untuk pendekatan single-step, model SARIMA lebih baik 49% dari model LSTM untuk prediksi dengan granularity data per jam. Namun, untuk granularity data per hari, performansi LSTM lebih baik 27% dari model SARIMA. Kemudian untuk pendekatan multi-step, SARIMA memberikan performansi yang lebih baik 30% daripada model LSTM untuk data per jam (< =24). Sedangkan untuk granularity data harian, model LSTM lebih baik 30% pada step 30 hari dan lebih baik 27% pada step 60 hari. Dan untuk data ekstrem, LSTM lebih baik 47% daripada SARIMA.   Abstract Time series prediction of weather data parameters involves forecasting future values based on historical weather patterns. This study addresses the limitations of previous research, such as constrained datasets, short prediction periods, restricted parameters, and the neglect of external factors that could enhance model accuracy. Utilizing Long Short-Term Memory (LSTM) networks and Seasonal AutoRegressive Integrated Moving Average (SARIMA) methods, the research focuses on predicting weather parameters like air pressure, temperature, and relative humidity using both single-step and multi-step approaches. The data is sourced from the BMKG Pinangsori Meteorological Station in Sibolga, covering an 8-year period with both hourly and daily granularity. The experimental findings reveal that LSTM and SARIMA each have their advantages depending on the context. In the single-step approach, the SARIMA model outperforms the LSTM model by 49% for predictions based on hourly data. Conversely, for daily data granularity, the LSTM model surpasses SARIMA by 27%. In the multi-step analysis, SARIMA demonstrates a 30% improvement over LSTM for hourly predictions (up to 24 hours). However, for daily granularity, the LSTM model excels, showing a 30% advantage at the 30-day prediction step and a 27% advantage at the 60-day step. Additionally, LSTM significantly outperforms SARIMA by 47% when dealing with extreme data.
Klasterisasi Berita Bahasa Indonesia Dengan Menggunakan K-Means Dan Word Embedding Simanjuntak, Humasak Tommy Argo; Silaban, Prince Ephraim Prabowo; Manurung, Joshua Koko Sarasi; Sormin, Venny Handayani
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 3: Juni 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2023106468

Abstract

Jumlah berita atau dokumen yang sangat melimpah merupakan sumber pengetahuan yang sangat berharga dan dapat digunakan untuk memperoleh wawasan dalam pengambilan keputusan. Namun, pertumbuhan jumlah berita dengan dimensi yang tinggi menjadi sebuah tantangan besar, yang menyebabkan sulitnya informasi pada berita dikategorikan secara efisien dan cepat. Kesulitan ini semakin kompleks dengan tidak adanya kelas atau label pada berita tersebut. Analisis konten dari berita yang belum memiliki kelas atau label dapat dilakukan dengan pendekatan data mining. Salah satu metode data mining yang dapat digunakan untuk mengelompokkan berita tanpa label, jumlah yang besar, dan sulit dilakukan secara manual adalah klastering. Klastering teks adalah salah satu metode penambangan data yang bertujuan untuk mengelompokkan dokumen berdasarkan kesamaan atau kemiripan di antara teks. Penelitian ini memberikan pendekatan baru dalam mengelompokkan berita Bahasa Indonesia dengan metode klastering, dimana ekstraksi fitur dilakukan melalui pendekatan Neural Network (Word Embedding) yang dapat menunjukkan kesamaan antar kata untuk mempertahankan semantik dan konteks dari kata yang ada pada berita. Sumber data yang digunakan adalah berita dari portal berita “Tempo” yang terdiri dari 520863 berita. Hasil penelitian menunjukkan bahwa jumlah klaster k = 4, dengan parameter Word Embedding: min_count=1 dan embedding_size=300 memberikan nilai silhouette coefficient terbaik sebesar 0.73. Hasil klasterisasi berita divisualisasikan dalam bentuk dimensi yang berbeda dan visualisasi World Cloud untuk menganalisis dan mengevaluasi metode yang diusulkan pada penelitian ini. AbstractThe enormous amount of news or documents is a precious source of knowledge and can be used to gain insight into decision-making. However, the growth in the number of news stories with high dimensions is a big challenge, making it difficult for information on the news to be categorized efficiently and quickly. This difficulty is further complicated by the absence of classes or labels on the news. Analysis of the content of news that does not yet have a class or label can be done with a data mining approach. The most used data mining method to group a tremendous amount of news without class labels is clustering. Text clustering is a data mining task that aims to group documents based on similarities. This study provides a new approach to classifying Indonesian news with the clustering method, where feature extraction is carried out through a Neural Network (Word Embedding) approach that can show similarities between words to maintain the semantics and context of the words in the news. The data source used is news from the news portal "Tempo," which consists of 5208063 news. The results showed that the number of clusters k = 4, with Word Embedding parameters: min_count=1 and embedding_size=300, produced the best silhouette coefficient value of 0.73. The results of news clustering were visualized in the form of different dimensions and World Cloud visualization to analyze and evaluate the proposed method.
Spatial Semantic Analysis and Origin-Destination Prediction Based on Extensive GPS Trajectory in Jakarta Simanjuntak, Humasak; Hutauruk, Agnes; Situmorang, Haryati; Silitonga, Yoshua
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 11 No 2 (2025): July (In Progress)
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v11i2.5388

Abstract

The rapid growth of mobility data from GPS trajectories offers unprecedented opportunities to gain deep insights into human mobility behavior, with significant implications for urban planning, traffic management, public transportation optimization, emergency response, and smart city development. However, a key challenge lies in transforming raw GPS trajectory data, consisting of sequences of coordinates and timestamps, into meaningful, context-rich information that can support analysis and decision making. This study proposes a semi-supervised framework to enhance the contextual and semantic understanding of journeys, using Grab Jakarta GPS trajectory data as a case study. The framework involves extracting origin-destination pairs, augmenting the data with temporal (day, time) and spatial (postal code, land use) contexts through public datasets, assigning cluster labels to characterize groups of journeys, analyzing mobility patterns, and ultimately predicting trip destinations. Origin-destination clustering, performed using the DBSCAN algorithm, identified five meaningful clusters, achieving the highest silhouette score of 0.56 with epsilon = 7.0 and min_samples = 5. Subsequently, a regression-based prediction model was developed, employing nine algorithms, including three deep learning approaches. The LSTM model demonstrated the best performance, yielding a mean squared error of 0.0053 and a coefficient of determination (R²) of 86.20% in predicting trip destinations. These findings highlight the potential of integrating spatial-temporal enrichment and machine learning to derive actionable insights from GPS trajectory data.
Co-Authors Adesty Saragih Arie Satia Dharma Arlinta Christy Barus Arlinta Christy Barus Banjarnahor, Wiwin Barus, Arlinta Claudia, Marwani Erisha Sitorus Febriani Gultom Gonzales, Helen Grace B. Goretti Situmorang Hansel Septiyan Pasaribu Hutauruk, Agnes Lowiska Simanjuntak Lubis, Anju Ucok Lumbanraja, Amelia Magdalena Panjaitan Manurung, Joshua Koko Sarasi Manurung, Ruth Christine Margaretha, Patricia Dian Monica Butarbutar Nancy Panjaitan Noramti Mardianti Manurung Panjaitan, Magdalena Panjaitan, Sintong Purba, Susi Rajagukguk, Nico Regita Ricton Samuel Sitorus Rosni Lumbantoruan Samosir, Gabriel Samuel Indra Gunawan Situmeang Siahaan, Lamsihar Silaban, Prince Ephraim Prabowo Silitonga, Yoshua Sintong Panjaitan Sitorus, Erisha Situmorang, Haryati Sormin, Venny Handayani Wesly Mailander Siagian Wiwin Sry Adinda Banjarnahor